chore: set transcribe_model_selection

.gitignore

@@ -6,6 +6,9 @@ __pycache__/
 # C extensions
 *.so
 
+#audios
+uploaded_audio/
+
 # Distribution / packaging
 .Python
 build/
@@ -144,3 +147,6 @@ venv.bak/
 .Trashes
 ehthumbs.db
 Thumbs.db
+
+#gcp
+gcp.json

api/middlewares/cors_middleware.py

@@ -0,0 +1,14 @@
+from fastapi.middleware.cors import CORSMiddleware
+
+def setup_cors(app):
+    origins = [
+        "http://localhost:3000",
+    ]
+
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=origins,
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )

api/routes/audio.py

@@ -1,7 +1,7 @@
 from fastapi import APIRouter, UploadFile, File, HTTPException
-from fastapi.responses import JSONResponse
-import shutil
 from pathlib import Path
+from api.services.transcribe_audio import transcribe_model_selection
+
 import os
 
 router = APIRouter()
@@ -15,12 +15,18 @@ def read_root():
 @router.post("/upload/")
 async def upload_audio(file: UploadFile = File(...)):
     try:
+        data = await file.read()
+
         Path(AUDIO_PATH).mkdir(parents=True, exist_ok=True)
+        path_to_audio = os.path.join(AUDIO_PATH, file.filename)
+
+        with open(path_to_audio, 'wb') as f:
+            f.write(data)
+
+        audio_text = transcribe_model_selection(path_to_audio)
 
-        with open(os.path(AUDIO_PATH, file.filename), "wb") as buffer:
-            shutil.copyfileobj(file.file, buffer)
-
         return {"filename": file.filename, "message": "File uploaded successfully!"}
     except Exception as e:
+        print(e)
         raise HTTPException(status_code=500, detail="File upload failed.")
 

api/services/transcribe_audio.py

@@ -1,22 +1,26 @@
 from google.cloud import speech
-from google.cloud.speech import enums, types
 
-def transcribe_audio(file_path):
+def transcribe_model_selection(speech_file: str) -> speech.RecognizeResponse:
+
     client = speech.SpeechClient()
 
-    with open(file_path, "rb") as audio_file:
+    with open(speech_file, "rb") as audio_file:
         content = audio_file.read()
 
-    audio = types.RecognitionAudio(content=content)
-    config = types.RecognitionConfig(
-        encoding=enums.RecognitionConfig.AudioEncondig.LINEAR16,
-        # TODO: Adjuste sample rate
+    audio = speech.RecognitionAudio(content=content)
+
+    config = speech.RecognitionConfig(
+        encoding=speech.RecognitionConfig.AudioEncoding.ENCODING_UNSPECIFIED,
         sample_rate_hertz=16000,
-        language_code="en-US"
+        language_code="en-US",
     )
 
     response = client.recognize(config=config, audio=audio)
+
+    for i, result in enumerate(response.results):
+        alternative = result.alternatives[0]
+        print("-" * 20)
+        print(f"First alternative of result {i}")
+        print(f"Transcript: {alternative.transcript}")
 
-    if response.results:
-        return response.results[0].alternatives[0].transcript
-    return ""
+    return response

main.py

@@ -1,6 +1,9 @@
 from fastapi import FastAPI
 from api.routes import audio
+from api.middlewares import cors_middleware
 
 app = FastAPI()
 
+cors_middleware.setup_cors(app)
+
 app.include_router(audio.router)

requirements.txt

@@ -1,6 +1,8 @@
 annotated-types==0.6.0
 anyio==3.7.1
+cachetools==5.3.2
 certifi==2023.7.22
+charset-normalizer==3.3.1
 click==8.1.7
 contourpy==1.1.1
 cycler==0.12.0
@@ -9,6 +11,12 @@ email-validator==2.1.0.post1
 exceptiongroup==1.1.3
 fastapi==0.104.0
 fonttools==4.43.0
+google-api-core==2.12.0
+google-auth==2.23.3
+google-cloud-speech==2.21.1
+googleapis-common-protos==1.61.0
+grpcio==1.59.0
+grpcio-status==1.59.0
 h11==0.14.0
 httpcore==0.18.0
 httptools==0.6.1
@@ -24,6 +32,10 @@ numpy==1.26.0
 orjson==3.9.9
 packaging==23.2
 Pillow==10.0.1
+proto-plus==1.22.3
+protobuf==4.24.4
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
 pydantic==2.4.2
 pydantic-extra-types==2.1.0
 pydantic-settings==2.0.3
@@ -33,12 +45,15 @@ python-dateutil==2.8.2
 python-dotenv==1.0.0
 python-multipart==0.0.6
 PyYAML==6.0.1
+requests==2.31.0
+rsa==4.9
 six==1.16.0
 sniffio==1.3.0
 starlette==0.27.0
 sympy==1.12
 typing_extensions==4.8.0
 ujson==5.8.0
+urllib3==2.0.7
 uvicorn==0.23.2
 uvloop==0.19.0
 watchfiles==0.21.0